Skip to content
HiAPI Docs
HiAPI
Playground Get API Key
English
English 中文

GPT-6.1 Sol API

POST Base URL: https://api.hiapi.ai /v1/responses

This model uses the OpenAI Responses endpoint. The same HiAPI API key works across enabled models; media models use /v1/tasks and a different request shape.

Model overview

Model IDgpt-6.1-sol
ProviderOpenAI
TypeText generation · streaming Responses
Reasoning effortslow / medium / high / xhigh / max
Examples / Playground effortmedium
PricingLive HiAPI token rates

Integrate OpenAI GPT-6.1 Sol through HiAPI streaming Responses for text generation and reasoning.

Production guidance

Request contract
  • Use POST /v1/responses with an input array, stream=true, and store=false.
  • Use low, medium, high, xhigh, or max for reasoning.effort. Omit temperature, top_p, and max_output_tokens.
  • The same HiAPI API key works across enabled models. Media models use /v1/tasks with a different request body.
  • This page documents streaming Responses only. Handle response.completed, response.incomplete, and response.failed separately.

Best suited for

Reasoning and code work

Choose an effort and consume text deltas as they arrive.

reasoning.effortinput

Request parameters

model string required

Use this exact public model ID.

example gpt-6.1-sol enum: gpt-6.1-sol
input array required

Message items. Replay the context needed for each turn.

stream boolean optional

Must be true. Process the response as SSE.

default true
store boolean optional

Must be false. Keep conversation state in your client.

default false
instructions string optional

Optional instructions for the response.

reasoning object optional

Reasoning configuration.

effort enum optional

Use low, medium, high, xhigh, or max. Other effort values are unsupported by this HiAPI integration.

example medium enum: lowmediumhighxhighmax

API examples

Request examples

Reasoning effort: low

Only the reasoning effort changes.

Request body
{
  "model": "gpt-6.1-sol",
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Summarize the three highest risks in this project plan."
        }
      ]
    }
  ],
  "stream": true,
  "store": false,
  "reasoning": {
    "effort": "low"
  }
}
Reasoning effort: high

Only the reasoning effort changes.

Request body
{
  "model": "gpt-6.1-sol",
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Summarize the three highest risks in this project plan."
        }
      ]
    }
  ],
  "stream": true,
  "store": false,
  "reasoning": {
    "effort": "high"
  }
}
Reasoning effort: xhigh

Only the reasoning effort changes.

Request body
{
  "model": "gpt-6.1-sol",
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Summarize the three highest risks in this project plan."
        }
      ]
    }
  ],
  "stream": true,
  "store": false,
  "reasoning": {
    "effort": "xhigh"
  }
}
Reasoning effort: max

Only the reasoning effort changes.

Request body
{
  "model": "gpt-6.1-sol",
  "input": [
    {
      "type": "message",
      "role": "user",
      "content": [
        {
          "type": "input_text",
          "text": "Summarize the three highest risks in this project plan."
        }
      ]
    }
  ],
  "stream": true,
  "store": false,
  "reasoning": {
    "effort": "max"
  }
}

Response schema

This illustrative SSE sequence shows text arriving before completion. Accumulate response.output_text.delta and read usage from response.completed. Handle incomplete and failed terminal events.

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":"OK"}

event: response.completed
data: {"type":"response.completed","response":{"id":"resp_example","model":"gpt-6.1-sol","status":"completed","output":[],"usage":{"input_tokens":100,"input_tokens_details":{"cached_tokens":0,"cache_write_tokens":0},"output_tokens":10,"total_tokens":110}}}
  1. Dispatch by event type and stop at a terminal response event.
  2. Accumulate text deltas; do not require response.completed.output to contain the full text.
  3. Read input_tokens, output_tokens, cache details, and total_tokens from usage. Count cache reads and writes only when usage reports them; reasoning_tokens are included in output_tokens. Above 272,000 input tokens, the long-context rates apply to the whole request. Use account logs for settled charges.

FAQ

Which endpoint and model ID should I use?

Use POST /v1/responses with model=gpt-6.1-sol, an input array, stream=true, and store=false.

Which reasoning efforts are supported?

Use low, medium, high, xhigh, or max. Other effort values are unsupported by this HiAPI integration.

Can I use sampling controls?

Omit temperature, top_p, and max_output_tokens for this integration.

How do I continue a conversation?

With store=false, replay the required context in input on each request.

How are tokens billed?

Read current input, output, cache-read, and cache-write rates on the live model page. Count cache reads and writes only when usage reports them; reasoning_tokens are included in output_tokens. View live pricing.

When does long-context pricing apply?

The threshold uses total input for the request, including reported cache reads and writes. At 272,000 tokens the standard tier still applies; from 272,001, the long-context rates apply to the whole request, including output and cache. View live pricing.

Next steps